commit 3899955d0e3105bfcd44f4cdeb23e4a4d9905628 Author: ModelHub XC Date: Sat Aug 8 04:21:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3-8B-Stroganoff-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..0193f34 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,50 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Stroganoff.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Stroganoff.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Stroganoff.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Stroganoff.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Stroganoff.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Stroganoff.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Stroganoff.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Stroganoff.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Stroganoff.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Stroganoff.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Stroganoff.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Stroganoff.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Stroganoff.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Stroganoff.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Stroganoff.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3-8B-Stroganoff.IQ3_M.gguf b/Llama-3-8B-Stroganoff.IQ3_M.gguf new file mode 100644 index 0000000..a409076 --- /dev/null +++ b/Llama-3-8B-Stroganoff.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fcb2f8babc60c57bc8dc45eafc9ea03a2b843aff761e21964540b9178344e984 +size 3784823520 diff --git a/Llama-3-8B-Stroganoff.IQ3_S.gguf b/Llama-3-8B-Stroganoff.IQ3_S.gguf new file mode 100644 index 0000000..918e1a0 --- /dev/null +++ b/Llama-3-8B-Stroganoff.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c5dea298053ce3291a1162c1e5c7510bf95b8a7620073a8e1c58cd1b140078f +size 3682325216 diff --git a/Llama-3-8B-Stroganoff.IQ3_XS.gguf b/Llama-3-8B-Stroganoff.IQ3_XS.gguf new file mode 100644 index 0000000..5cc6c73 --- /dev/null +++ b/Llama-3-8B-Stroganoff.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6fd8cecf72c6ff2f5504a4e77545d02975252e4326d4371f435c29951f2772e4 +size 3518747360 diff --git a/Llama-3-8B-Stroganoff.IQ4_XS.gguf b/Llama-3-8B-Stroganoff.IQ4_XS.gguf new file mode 100644 index 0000000..28332a6 --- /dev/null +++ b/Llama-3-8B-Stroganoff.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ea5dbc87c0648a4be4d02bc6b29f68c32d27dd84f6fd38c190586ebca15ddb4 +size 4484362976 diff --git a/Llama-3-8B-Stroganoff.Q2_K.gguf b/Llama-3-8B-Stroganoff.Q2_K.gguf new file mode 100644 index 0000000..e1fa96c --- /dev/null +++ b/Llama-3-8B-Stroganoff.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a913130c9196ab683c49a739daf89c3b08bc91d18add43c83c5a69c80b2ee18 +size 3179131616 diff --git a/Llama-3-8B-Stroganoff.Q3_K_L.gguf b/Llama-3-8B-Stroganoff.Q3_K_L.gguf new file mode 100644 index 0000000..a0694db --- /dev/null +++ b/Llama-3-8B-Stroganoff.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7661063363d05f44d5fd814ac2fd03f25a71afc9e383b6c8222567601c715a94 +size 4321956576 diff --git a/Llama-3-8B-Stroganoff.Q3_K_M.gguf b/Llama-3-8B-Stroganoff.Q3_K_M.gguf new file mode 100644 index 0000000..3e1f4d6 --- /dev/null +++ b/Llama-3-8B-Stroganoff.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f1bf6cbe58b3fd0228a4169d6366dcea4701e6f47f96bcc8518c94f43046c8b +size 4018918112 diff --git a/Llama-3-8B-Stroganoff.Q3_K_S.gguf b/Llama-3-8B-Stroganoff.Q3_K_S.gguf new file mode 100644 index 0000000..0afadd3 --- /dev/null +++ b/Llama-3-8B-Stroganoff.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34e3a490f5b19497620e7e372f1feba874c74c8171fbe66c2355ae4f32d620a6 +size 3664499424 diff --git a/Llama-3-8B-Stroganoff.Q4_K_M.gguf b/Llama-3-8B-Stroganoff.Q4_K_M.gguf new file mode 100644 index 0000000..225a17a --- /dev/null +++ b/Llama-3-8B-Stroganoff.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f67cc68c5dd1914b5c4682613f1c68213ff793fa172cd875e530b36c1cf851e +size 4920734432 diff --git a/Llama-3-8B-Stroganoff.Q4_K_S.gguf b/Llama-3-8B-Stroganoff.Q4_K_S.gguf new file mode 100644 index 0000000..8ac21b4 --- /dev/null +++ b/Llama-3-8B-Stroganoff.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ddb938205573e2ed57a9976a587cc313f663d40e1b1ec5b3b591e80621a3367 +size 4692669152 diff --git a/Llama-3-8B-Stroganoff.Q5_K_M.gguf b/Llama-3-8B-Stroganoff.Q5_K_M.gguf new file mode 100644 index 0000000..0c26a08 --- /dev/null +++ b/Llama-3-8B-Stroganoff.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a84616d4c08b6baf612f1779145d5bbf9943e8e008da95a7d0d80ade1a9e6daf +size 5732987616 diff --git a/Llama-3-8B-Stroganoff.Q5_K_S.gguf b/Llama-3-8B-Stroganoff.Q5_K_S.gguf new file mode 100644 index 0000000..6e9eafd --- /dev/null +++ b/Llama-3-8B-Stroganoff.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c93f4677018abdcb20591164296ca5be3962a5dc72d212fcf0877d5043be9bc9 +size 5599294176 diff --git a/Llama-3-8B-Stroganoff.Q6_K.gguf b/Llama-3-8B-Stroganoff.Q6_K.gguf new file mode 100644 index 0000000..476d9ca --- /dev/null +++ b/Llama-3-8B-Stroganoff.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb79fc933d577f92f22585a6b8449568d8bf88b11de9cb50dd8b8fc010a75d2b +size 6596006624 diff --git a/Llama-3-8B-Stroganoff.Q8_0.gguf b/Llama-3-8B-Stroganoff.Q8_0.gguf new file mode 100644 index 0000000..045e921 --- /dev/null +++ b/Llama-3-8B-Stroganoff.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6bda0a87e00c8ca0fe4384999b245eed4998d71b12a3105a87d127d5db131ca2 +size 8540771040 diff --git a/Llama-3-8B-Stroganoff.f16.gguf b/Llama-3-8B-Stroganoff.f16.gguf new file mode 100644 index 0000000..9a09daa --- /dev/null +++ b/Llama-3-8B-Stroganoff.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:078b7d18c130e9e526d7a194a019e45ec535973a186360421137561628524067 +size 16068891360 diff --git a/README.md b/README.md new file mode 100644 index 0000000..22e85ae --- /dev/null +++ b/README.md @@ -0,0 +1,74 @@ +--- +base_model: HiroseKoichi/Llama-3-8B-Stroganoff +language: +- en +library_name: transformers +license: llama3 +quantized_by: mradermacher +tags: +- nsfw +- not-for-all-audiences +- llama-3 +- text-generation-inference +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/HiroseKoichi/Llama-3-8B-Stroganoff + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama-3-8B-Stroganoff-i1-GGUF +## Usage + +If you are unsure how to use GGUF files, refer to one of [TheBloke's +READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for +more details, including on how to concatenate multi-part files. + +## Provided Quants + +(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) + +| Link | Type | Size/GB | Notes | +|:-----|:-----|--------:|:------| +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Stroganoff-GGUF/resolve/main/Llama-3-8B-Stroganoff.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Stroganoff-GGUF/resolve/main/Llama-3-8B-Stroganoff.IQ3_XS.gguf) | IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Stroganoff-GGUF/resolve/main/Llama-3-8B-Stroganoff.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Stroganoff-GGUF/resolve/main/Llama-3-8B-Stroganoff.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Stroganoff-GGUF/resolve/main/Llama-3-8B-Stroganoff.IQ3_M.gguf) | IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Stroganoff-GGUF/resolve/main/Llama-3-8B-Stroganoff.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Stroganoff-GGUF/resolve/main/Llama-3-8B-Stroganoff.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Stroganoff-GGUF/resolve/main/Llama-3-8B-Stroganoff.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Stroganoff-GGUF/resolve/main/Llama-3-8B-Stroganoff.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Stroganoff-GGUF/resolve/main/Llama-3-8B-Stroganoff.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Stroganoff-GGUF/resolve/main/Llama-3-8B-Stroganoff.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Stroganoff-GGUF/resolve/main/Llama-3-8B-Stroganoff.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Stroganoff-GGUF/resolve/main/Llama-3-8B-Stroganoff.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Stroganoff-GGUF/resolve/main/Llama-3-8B-Stroganoff.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Stroganoff-GGUF/resolve/main/Llama-3-8B-Stroganoff.f16.gguf) | f16 | 16.2 | 16 bpw, overkill | + +Here is a handy graph by ikawrakow comparing some lower-quality quant +types (lower is better): + +![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) + +And here are Artefact2's thoughts on the matter: +https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 + +## FAQ / Model Request + +See https://huggingface.co/mradermacher/model_requests for some answers to +questions you might have and/or if you want some other model quantized. + +## Thanks + +I thank my company, [nethype GmbH](https://www.nethype.de/), for letting +me use its servers and providing upgrades to my workstation to enable +this work in my free time. + +